CtrlK
BlogDocsLog inGet started
Tessl Logo

koog-assistant

Concise general-purpose assistant powered by JetBrains Koog. Use when a brief, focused answer is preferable to long-form output.

53

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./modules/skills/src/main/resources/META-INF/skills/koog-assistant/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is maximally lean and its one instruction is unambiguous, but the skill is behaviorally thin — a word limit and persona sentence with no examples or guidance on what concise output should look like. It qualifies for the simple-skill exceptions on workflow and disclosure, with actionability the only real gap.

Suggestions

Add one short example of a desired concise response (a question and a 2-3 sentence model answer) to make the expected output style concrete.

Clarify edge behavior beyond the word limit, e.g., how to handle multi-part questions or code-heavy answers where 500 words is impractical.

DimensionReasoningScore

Conciseness

The body is two sentences with zero padding and no explanation of concepts Claude already knows; every token (persona, word limit, exception clause) earns its place, matching the lean-and-efficient anchor.

5 / 5

Actionability

"Keep responses under 500 words unless asked for more detail" is a concrete, executable rule with a numeric threshold, but there is no example of the desired output style and no coverage of common cases, placing it at the mostly-executable anchor rather than fully-executable.

4 / 5

Workflow Clarity

This is a simple single-purpose skill and its single action — respond concisely, under 500 words, with an explicit exception — is unambiguous, so the simple-skill exception applies.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and nothing that belongs in a separate file, so inline placement is appropriate; however there are no sections or organization at all, leaving it just below the well-organized anchor.

4 / 5

Total

18

/

20

Passed

Description

33%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has the right structural shape (what + "Use when..." trigger) but is too generic to be useful: it names no concrete capabilities and its trigger contains no phrases a user would naturally say. As a general-purpose assistant it also has high conflict risk with nearly every other skill.

Suggestions

List 2-3 concrete capabilities or behaviors (e.g., 'Summarizes answers in under 500 words, answers factual questions directly') instead of the generic 'concise general-purpose assistant'.

Rewrite the trigger with natural user phrasing and synonyms, e.g., 'Use when the user asks for a short answer, a summary, a quick explanation, or says "keep it brief" / "in one paragraph".'

Narrow the stated scope or add distinguishing signals (specific task types, output formats) so the skill does not fire for nearly any request.

DimensionReasoningScore

Specificity

"Concise general-purpose assistant" names the domain but lists no concrete actions or capabilities; it is only slightly more informative than the purely abstract "Helps with documents" anchor, so it sits between anchors 1 and 2.

2 / 5

Completeness

Both a "what" ("concise general-purpose assistant") and a "when" ("Use when...") are present, but the what is vague and the when is abstract; this falls between anchor 3 (clear what, weak when) and anchor 4 (both present, when could be more specific).

3 / 5

Trigger Term Quality

The trigger "Use when a brief, focused answer is preferable to long-form output" is abstract phrasing a user would not naturally say; there are no natural keywords, synonyms, or concrete terms beyond generic language.

2 / 5

Distinctiveness Conflict Risk

"general-purpose assistant" overlaps with virtually any other skill; only the brevity preference provides any distinguishing signal, matching the "very broad; high overlap risk" anchor.

2 / 5

Total

9

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
Atmosphere/atmosphere
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.